---
language:
- en
license: mit
tags:
- sentence-transformers
- multi-vector
- colbert
- late-interaction
- generated_from_trainer
- dataset_size:501907
- loss:MultiVectorMultipleNegativesRankingLoss
base_model: prajjwal1/bert-tiny
widget:
- text: 'Kroger Pharmacy - Keller 976 Keller Pkwy, Keller TX 76248 Phone Number: (817)
431-5178'
- text: Moyie Springs, Idaho. Moyie Springs is a city in Boundary County, Idaho, United
States. The population was 718 at the 2010 census.
- text: cunningham funeral home in colbert ok
- text: A.O. Smith stock price target raised to $60 from $58 at Boenning & Scattergood.
8:26 a.m. July 26, 2017 - Tomi Kilgore
- text: 'There are 140 calories in a 4 pieces serving of Kirkland Signature Four Cheese
Ravioli. Calorie breakdown: 45% fat, 31% carbs, 24% protein.'
datasets:
- sentence-transformers/msmarco-bm25
pipeline_tag: feature-extraction
library_name: sentence-transformers
metrics:
- maxsim_accuracy@1
- maxsim_accuracy@3
- maxsim_accuracy@5
- maxsim_accuracy@10
- maxsim_precision@1
- maxsim_precision@3
- maxsim_precision@5
- maxsim_precision@10
- maxsim_recall@1
- maxsim_recall@3
- maxsim_recall@5
- maxsim_recall@10
- maxsim_ndcg@10
- maxsim_mrr@10
- maxsim_map@100
model-index:
- name: BERT tiny multi-vector encoder trained on MS MARCO
results:
- task:
type: multi-vector-information-retrieval
name: Multi Vector Information Retrieval
dataset:
name: NanoMSMARCO
type: NanoMSMARCO
metrics:
- type: maxsim_accuracy@1
value: 0.16
name: Maxsim Accuracy@1
- type: maxsim_accuracy@3
value: 0.32
name: Maxsim Accuracy@3
- type: maxsim_accuracy@5
value: 0.42
name: Maxsim Accuracy@5
- type: maxsim_accuracy@10
value: 0.7
name: Maxsim Accuracy@10
- type: maxsim_precision@1
value: 0.16
name: Maxsim Precision@1
- type: maxsim_precision@3
value: 0.10666666666666666
name: Maxsim Precision@3
- type: maxsim_precision@5
value: 0.084
name: Maxsim Precision@5
- type: maxsim_precision@10
value: 0.07
name: Maxsim Precision@10
- type: maxsim_recall@1
value: 0.16
name: Maxsim Recall@1
- type: maxsim_recall@3
value: 0.32
name: Maxsim Recall@3
- type: maxsim_recall@5
value: 0.42
name: Maxsim Recall@5
- type: maxsim_recall@10
value: 0.7
name: Maxsim Recall@10
- type: maxsim_ndcg@10
value: 0.3858968432351718
name: Maxsim Ndcg@10
- type: maxsim_mrr@10
value: 0.292015873015873
name: Maxsim Mrr@10
- type: maxsim_map@100
value: 0.3048587220806822
name: Maxsim Map@100
- type: maxsim_accuracy@1
value: 0.16
name: Maxsim Accuracy@1
- type: maxsim_accuracy@3
value: 0.32
name: Maxsim Accuracy@3
- type: maxsim_accuracy@5
value: 0.42
name: Maxsim Accuracy@5
- type: maxsim_accuracy@10
value: 0.7
name: Maxsim Accuracy@10
- type: maxsim_precision@1
value: 0.16
name: Maxsim Precision@1
- type: maxsim_precision@3
value: 0.10666666666666666
name: Maxsim Precision@3
- type: maxsim_precision@5
value: 0.084
name: Maxsim Precision@5
- type: maxsim_precision@10
value: 0.07
name: Maxsim Precision@10
- type: maxsim_recall@1
value: 0.16
name: Maxsim Recall@1
- type: maxsim_recall@3
value: 0.32
name: Maxsim Recall@3
- type: maxsim_recall@5
value: 0.42
name: Maxsim Recall@5
- type: maxsim_recall@10
value: 0.7
name: Maxsim Recall@10
- type: maxsim_ndcg@10
value: 0.3858968432351718
name: Maxsim Ndcg@10
- type: maxsim_mrr@10
value: 0.292015873015873
name: Maxsim Mrr@10
- type: maxsim_map@100
value: 0.3048587220806822
name: Maxsim Map@100
- task:
type: multi-vector-information-retrieval
name: Multi Vector Information Retrieval
dataset:
name: NanoNQ
type: NanoNQ
metrics:
- type: maxsim_accuracy@1
value: 0.28
name: Maxsim Accuracy@1
- type: maxsim_accuracy@3
value: 0.4
name: Maxsim Accuracy@3
- type: maxsim_accuracy@5
value: 0.48
name: Maxsim Accuracy@5
- type: maxsim_accuracy@10
value: 0.66
name: Maxsim Accuracy@10
- type: maxsim_precision@1
value: 0.28
name: Maxsim Precision@1
- type: maxsim_precision@3
value: 0.13333333333333333
name: Maxsim Precision@3
- type: maxsim_precision@5
value: 0.09600000000000002
name: Maxsim Precision@5
- type: maxsim_precision@10
value: 0.066
name: Maxsim Precision@10
- type: maxsim_recall@1
value: 0.27
name: Maxsim Recall@1
- type: maxsim_recall@3
value: 0.39
name: Maxsim Recall@3
- type: maxsim_recall@5
value: 0.46
name: Maxsim Recall@5
- type: maxsim_recall@10
value: 0.61
name: Maxsim Recall@10
- type: maxsim_ndcg@10
value: 0.42995107279160477
name: Maxsim Ndcg@10
- type: maxsim_mrr@10
value: 0.3832698412698412
name: Maxsim Mrr@10
- type: maxsim_map@100
value: 0.3841358170885305
name: Maxsim Map@100
- type: maxsim_accuracy@1
value: 0.28
name: Maxsim Accuracy@1
- type: maxsim_accuracy@3
value: 0.4
name: Maxsim Accuracy@3
- type: maxsim_accuracy@5
value: 0.48
name: Maxsim Accuracy@5
- type: maxsim_accuracy@10
value: 0.66
name: Maxsim Accuracy@10
- type: maxsim_precision@1
value: 0.28
name: Maxsim Precision@1
- type: maxsim_precision@3
value: 0.13333333333333333
name: Maxsim Precision@3
- type: maxsim_precision@5
value: 0.09600000000000002
name: Maxsim Precision@5
- type: maxsim_precision@10
value: 0.066
name: Maxsim Precision@10
- type: maxsim_recall@1
value: 0.27
name: Maxsim Recall@1
- type: maxsim_recall@3
value: 0.39
name: Maxsim Recall@3
- type: maxsim_recall@5
value: 0.46
name: Maxsim Recall@5
- type: maxsim_recall@10
value: 0.61
name: Maxsim Recall@10
- type: maxsim_ndcg@10
value: 0.42995107279160477
name: Maxsim Ndcg@10
- type: maxsim_mrr@10
value: 0.3832698412698412
name: Maxsim Mrr@10
- type: maxsim_map@100
value: 0.3841358170885305
name: Maxsim Map@100
- task:
type: multi-vector-information-retrieval
name: Multi Vector Information Retrieval
dataset:
name: NanoFiQA2018
type: NanoFiQA2018
metrics:
- type: maxsim_accuracy@1
value: 0.26
name: Maxsim Accuracy@1
- type: maxsim_accuracy@3
value: 0.4
name: Maxsim Accuracy@3
- type: maxsim_accuracy@5
value: 0.48
name: Maxsim Accuracy@5
- type: maxsim_accuracy@10
value: 0.58
name: Maxsim Accuracy@10
- type: maxsim_precision@1
value: 0.26
name: Maxsim Precision@1
- type: maxsim_precision@3
value: 0.18
name: Maxsim Precision@3
- type: maxsim_precision@5
value: 0.132
name: Maxsim Precision@5
- type: maxsim_precision@10
value: 0.08
name: Maxsim Precision@10
- type: maxsim_recall@1
value: 0.12285714285714285
name: Maxsim Recall@1
- type: maxsim_recall@3
value: 0.251047619047619
name: Maxsim Recall@3
- type: maxsim_recall@5
value: 0.3117142857142857
name: Maxsim Recall@5
- type: maxsim_recall@10
value: 0.38704761904761903
name: Maxsim Recall@10
- type: maxsim_ndcg@10
value: 0.3027040168258662
name: Maxsim Ndcg@10
- type: maxsim_mrr@10
value: 0.36041269841269835
name: Maxsim Mrr@10
- type: maxsim_map@100
value: 0.24465363135397997
name: Maxsim Map@100
- type: maxsim_accuracy@1
value: 0.26
name: Maxsim Accuracy@1
- type: maxsim_accuracy@3
value: 0.4
name: Maxsim Accuracy@3
- type: maxsim_accuracy@5
value: 0.48
name: Maxsim Accuracy@5
- type: maxsim_accuracy@10
value: 0.58
name: Maxsim Accuracy@10
- type: maxsim_precision@1
value: 0.26
name: Maxsim Precision@1
- type: maxsim_precision@3
value: 0.18
name: Maxsim Precision@3
- type: maxsim_precision@5
value: 0.132
name: Maxsim Precision@5
- type: maxsim_precision@10
value: 0.08
name: Maxsim Precision@10
- type: maxsim_recall@1
value: 0.12285714285714285
name: Maxsim Recall@1
- type: maxsim_recall@3
value: 0.251047619047619
name: Maxsim Recall@3
- type: maxsim_recall@5
value: 0.3117142857142857
name: Maxsim Recall@5
- type: maxsim_recall@10
value: 0.38704761904761903
name: Maxsim Recall@10
- type: maxsim_ndcg@10
value: 0.3027040168258662
name: Maxsim Ndcg@10
- type: maxsim_mrr@10
value: 0.36041269841269835
name: Maxsim Mrr@10
- type: maxsim_map@100
value: 0.24465363135397997
name: Maxsim Map@100
- task:
type: multi-vector-nano-beir
name: Multi Vector Nano BEIR
dataset:
name: NanoBEIR mean
type: NanoBEIR_mean
metrics:
- type: maxsim_accuracy@1
value: 0.23333333333333336
name: Maxsim Accuracy@1
- type: maxsim_accuracy@3
value: 0.37333333333333335
name: Maxsim Accuracy@3
- type: maxsim_accuracy@5
value: 0.45999999999999996
name: Maxsim Accuracy@5
- type: maxsim_accuracy@10
value: 0.6466666666666666
name: Maxsim Accuracy@10
- type: maxsim_precision@1
value: 0.23333333333333336
name: Maxsim Precision@1
- type: maxsim_precision@3
value: 0.13999999999999999
name: Maxsim Precision@3
- type: maxsim_precision@5
value: 0.10400000000000002
name: Maxsim Precision@5
- type: maxsim_precision@10
value: 0.07200000000000001
name: Maxsim Precision@10
- type: maxsim_recall@1
value: 0.1842857142857143
name: Maxsim Recall@1
- type: maxsim_recall@3
value: 0.32034920634920633
name: Maxsim Recall@3
- type: maxsim_recall@5
value: 0.3972380952380952
name: Maxsim Recall@5
- type: maxsim_recall@10
value: 0.5656825396825397
name: Maxsim Recall@10
- type: maxsim_ndcg@10
value: 0.37285064428421427
name: Maxsim Ndcg@10
- type: maxsim_mrr@10
value: 0.34523280423280417
name: Maxsim Mrr@10
- type: maxsim_map@100
value: 0.31121605684106424
name: Maxsim Map@100
- type: maxsim_accuracy@1
value: 0.40367346938775506
name: Maxsim Accuracy@1
- type: maxsim_accuracy@3
value: 0.5673469387755101
name: Maxsim Accuracy@3
- type: maxsim_accuracy@5
value: 0.6259654631083202
name: Maxsim Accuracy@5
- type: maxsim_accuracy@10
value: 0.7445839874411302
name: Maxsim Accuracy@10
- type: maxsim_precision@1
value: 0.40367346938775506
name: Maxsim Precision@1
- type: maxsim_precision@3
value: 0.2545368916797488
name: Maxsim Precision@3
- type: maxsim_precision@5
value: 0.1988320251177394
name: Maxsim Precision@5
- type: maxsim_precision@10
value: 0.14285400313971744
name: Maxsim Precision@10
- type: maxsim_recall@1
value: 0.2296541932962195
name: Maxsim Recall@1
- type: maxsim_recall@3
value: 0.3527886883553923
name: Maxsim Recall@3
- type: maxsim_recall@5
value: 0.4044498317393773
name: Maxsim Recall@5
- type: maxsim_recall@10
value: 0.5012192071371501
name: Maxsim Recall@10
- type: maxsim_ndcg@10
value: 0.44684493129737013
name: Maxsim Ndcg@10
- type: maxsim_mrr@10
value: 0.506674777603349
name: Maxsim Mrr@10
- type: maxsim_map@100
value: 0.37732753591032614
name: Maxsim Map@100
- task:
type: multi-vector-information-retrieval
name: Multi Vector Information Retrieval
dataset:
name: NanoClimateFEVER
type: NanoClimateFEVER
metrics:
- type: maxsim_accuracy@1
value: 0.18
name: Maxsim Accuracy@1
- type: maxsim_accuracy@3
value: 0.3
name: Maxsim Accuracy@3
- type: maxsim_accuracy@5
value: 0.34
name: Maxsim Accuracy@5
- type: maxsim_accuracy@10
value: 0.5
name: Maxsim Accuracy@10
- type: maxsim_precision@1
value: 0.18
name: Maxsim Precision@1
- type: maxsim_precision@3
value: 0.1
name: Maxsim Precision@3
- type: maxsim_precision@5
value: 0.07600000000000001
name: Maxsim Precision@5
- type: maxsim_precision@10
value: 0.05800000000000001
name: Maxsim Precision@10
- type: maxsim_recall@1
value: 0.09166666666666667
name: Maxsim Recall@1
- type: maxsim_recall@3
value: 0.12999999999999998
name: Maxsim Recall@3
- type: maxsim_recall@5
value: 0.16
name: Maxsim Recall@5
- type: maxsim_recall@10
value: 0.2383333333333333
name: Maxsim Recall@10
- type: maxsim_ndcg@10
value: 0.19191034232336726
name: Maxsim Ndcg@10
- type: maxsim_mrr@10
value: 0.2662698412698412
name: Maxsim Mrr@10
- type: maxsim_map@100
value: 0.14946591363353165
name: Maxsim Map@100
- task:
type: multi-vector-information-retrieval
name: Multi Vector Information Retrieval
dataset:
name: NanoDBPedia
type: NanoDBPedia
metrics:
- type: maxsim_accuracy@1
value: 0.62
name: Maxsim Accuracy@1
- type: maxsim_accuracy@3
value: 0.78
name: Maxsim Accuracy@3
- type: maxsim_accuracy@5
value: 0.84
name: Maxsim Accuracy@5
- type: maxsim_accuracy@10
value: 0.94
name: Maxsim Accuracy@10
- type: maxsim_precision@1
value: 0.62
name: Maxsim Precision@1
- type: maxsim_precision@3
value: 0.4733333333333333
name: Maxsim Precision@3
- type: maxsim_precision@5
value: 0.44800000000000006
name: Maxsim Precision@5
- type: maxsim_precision@10
value: 0.39199999999999996
name: Maxsim Precision@10
- type: maxsim_recall@1
value: 0.052136771709552124
name: Maxsim Recall@1
- type: maxsim_recall@3
value: 0.11703776658357738
name: Maxsim Recall@3
- type: maxsim_recall@5
value: 0.16684861747261473
name: Maxsim Recall@5
- type: maxsim_recall@10
value: 0.2876252581653851
name: Maxsim Recall@10
- type: maxsim_ndcg@10
value: 0.4820307033364284
name: Maxsim Ndcg@10
- type: maxsim_mrr@10
value: 0.7217380952380953
name: Maxsim Mrr@10
- type: maxsim_map@100
value: 0.3543191098253603
name: Maxsim Map@100
- task:
type: multi-vector-information-retrieval
name: Multi Vector Information Retrieval
dataset:
name: NanoFEVER
type: NanoFEVER
metrics:
- type: maxsim_accuracy@1
value: 0.56
name: Maxsim Accuracy@1
- type: maxsim_accuracy@3
value: 0.72
name: Maxsim Accuracy@3
- type: maxsim_accuracy@5
value: 0.82
name: Maxsim Accuracy@5
- type: maxsim_accuracy@10
value: 0.86
name: Maxsim Accuracy@10
- type: maxsim_precision@1
value: 0.56
name: Maxsim Precision@1
- type: maxsim_precision@3
value: 0.24666666666666665
name: Maxsim Precision@3
- type: maxsim_precision@5
value: 0.172
name: Maxsim Precision@5
- type: maxsim_precision@10
value: 0.092
name: Maxsim Precision@10
- type: maxsim_recall@1
value: 0.5266666666666667
name: Maxsim Recall@1
- type: maxsim_recall@3
value: 0.6766666666666667
name: Maxsim Recall@3
- type: maxsim_recall@5
value: 0.7833333333333333
name: Maxsim Recall@5
- type: maxsim_recall@10
value: 0.8233333333333333
name: Maxsim Recall@10
- type: maxsim_ndcg@10
value: 0.6792624024637341
name: Maxsim Ndcg@10
- type: maxsim_mrr@10
value: 0.6485555555555556
name: Maxsim Mrr@10
- type: maxsim_map@100
value: 0.6348848591340011
name: Maxsim Map@100
- task:
type: multi-vector-information-retrieval
name: Multi Vector Information Retrieval
dataset:
name: NanoHotpotQA
type: NanoHotpotQA
metrics:
- type: maxsim_accuracy@1
value: 0.72
name: Maxsim Accuracy@1
- type: maxsim_accuracy@3
value: 0.9
name: Maxsim Accuracy@3
- type: maxsim_accuracy@5
value: 0.92
name: Maxsim Accuracy@5
- type: maxsim_accuracy@10
value: 0.96
name: Maxsim Accuracy@10
- type: maxsim_precision@1
value: 0.72
name: Maxsim Precision@1
- type: maxsim_precision@3
value: 0.41333333333333333
name: Maxsim Precision@3
- type: maxsim_precision@5
value: 0.268
name: Maxsim Precision@5
- type: maxsim_precision@10
value: 0.148
name: Maxsim Precision@10
- type: maxsim_recall@1
value: 0.36
name: Maxsim Recall@1
- type: maxsim_recall@3
value: 0.62
name: Maxsim Recall@3
- type: maxsim_recall@5
value: 0.67
name: Maxsim Recall@5
- type: maxsim_recall@10
value: 0.74
name: Maxsim Recall@10
- type: maxsim_ndcg@10
value: 0.6839586445702376
name: Maxsim Ndcg@10
- type: maxsim_mrr@10
value: 0.8070238095238095
name: Maxsim Mrr@10
- type: maxsim_map@100
value: 0.6020088740548019
name: Maxsim Map@100
- task:
type: multi-vector-information-retrieval
name: Multi Vector Information Retrieval
dataset:
name: NanoNFCorpus
type: NanoNFCorpus
metrics:
- type: maxsim_accuracy@1
value: 0.42
name: Maxsim Accuracy@1
- type: maxsim_accuracy@3
value: 0.52
name: Maxsim Accuracy@3
- type: maxsim_accuracy@5
value: 0.52
name: Maxsim Accuracy@5
- type: maxsim_accuracy@10
value: 0.6
name: Maxsim Accuracy@10
- type: maxsim_precision@1
value: 0.42
name: Maxsim Precision@1
- type: maxsim_precision@3
value: 0.32666666666666666
name: Maxsim Precision@3
- type: maxsim_precision@5
value: 0.26799999999999996
name: Maxsim Precision@5
- type: maxsim_precision@10
value: 0.22399999999999998
name: Maxsim Precision@10
- type: maxsim_recall@1
value: 0.044696247294946014
name: Maxsim Recall@1
- type: maxsim_recall@3
value: 0.07181046561572595
name: Maxsim Recall@3
- type: maxsim_recall@5
value: 0.0834824676415163
name: Maxsim Recall@5
- type: maxsim_recall@10
value: 0.10608315478868971
name: Maxsim Recall@10
- type: maxsim_ndcg@10
value: 0.28518605272369923
name: Maxsim Ndcg@10
- type: maxsim_mrr@10
value: 0.4765238095238095
name: Maxsim Mrr@10
- type: maxsim_map@100
value: 0.12589300813746968
name: Maxsim Map@100
- task:
type: multi-vector-information-retrieval
name: Multi Vector Information Retrieval
dataset:
name: NanoQuoraRetrieval
type: NanoQuoraRetrieval
metrics:
- type: maxsim_accuracy@1
value: 0.74
name: Maxsim Accuracy@1
- type: maxsim_accuracy@3
value: 0.88
name: Maxsim Accuracy@3
- type: maxsim_accuracy@5
value: 0.9
name: Maxsim Accuracy@5
- type: maxsim_accuracy@10
value: 0.92
name: Maxsim Accuracy@10
- type: maxsim_precision@1
value: 0.74
name: Maxsim Precision@1
- type: maxsim_precision@3
value: 0.35999999999999993
name: Maxsim Precision@3
- type: maxsim_precision@5
value: 0.22799999999999998
name: Maxsim Precision@5
- type: maxsim_precision@10
value: 0.12
name: Maxsim Precision@10
- type: maxsim_recall@1
value: 0.654
name: Maxsim Recall@1
- type: maxsim_recall@3
value: 0.8586666666666667
name: Maxsim Recall@3
- type: maxsim_recall@5
value: 0.8859999999999999
name: Maxsim Recall@5
- type: maxsim_recall@10
value: 0.9126666666666666
name: Maxsim Recall@10
- type: maxsim_ndcg@10
value: 0.8354929187617376
name: Maxsim Ndcg@10
- type: maxsim_mrr@10
value: 0.8162222222222222
name: Maxsim Mrr@10
- type: maxsim_map@100
value: 0.8099312372179969
name: Maxsim Map@100
- task:
type: multi-vector-information-retrieval
name: Multi Vector Information Retrieval
dataset:
name: NanoSCIDOCS
type: NanoSCIDOCS
metrics:
- type: maxsim_accuracy@1
value: 0.26
name: Maxsim Accuracy@1
- type: maxsim_accuracy@3
value: 0.42
name: Maxsim Accuracy@3
- type: maxsim_accuracy@5
value: 0.52
name: Maxsim Accuracy@5
- type: maxsim_accuracy@10
value: 0.74
name: Maxsim Accuracy@10
- type: maxsim_precision@1
value: 0.26
name: Maxsim Precision@1
- type: maxsim_precision@3
value: 0.18
name: Maxsim Precision@3
- type: maxsim_precision@5
value: 0.15200000000000002
name: Maxsim Precision@5
- type: maxsim_precision@10
value: 0.11800000000000001
name: Maxsim Precision@10
- type: maxsim_recall@1
value: 0.054000000000000006
name: Maxsim Recall@1
- type: maxsim_recall@3
value: 0.11000000000000001
name: Maxsim Recall@3
- type: maxsim_recall@5
value: 0.15400000000000003
name: Maxsim Recall@5
- type: maxsim_recall@10
value: 0.23999999999999996
name: Maxsim Recall@10
- type: maxsim_ndcg@10
value: 0.22168572688545177
name: Maxsim Ndcg@10
- type: maxsim_mrr@10
value: 0.38710317460317456
name: Maxsim Mrr@10
- type: maxsim_map@100
value: 0.15605007993528686
name: Maxsim Map@100
- task:
type: multi-vector-information-retrieval
name: Multi Vector Information Retrieval
dataset:
name: NanoArguAna
type: NanoArguAna
metrics:
- type: maxsim_accuracy@1
value: 0.18
name: Maxsim Accuracy@1
- type: maxsim_accuracy@3
value: 0.38
name: Maxsim Accuracy@3
- type: maxsim_accuracy@5
value: 0.42
name: Maxsim Accuracy@5
- type: maxsim_accuracy@10
value: 0.56
name: Maxsim Accuracy@10
- type: maxsim_precision@1
value: 0.18
name: Maxsim Precision@1
- type: maxsim_precision@3
value: 0.12666666666666665
name: Maxsim Precision@3
- type: maxsim_precision@5
value: 0.084
name: Maxsim Precision@5
- type: maxsim_precision@10
value: 0.05600000000000001
name: Maxsim Precision@10
- type: maxsim_recall@1
value: 0.18
name: Maxsim Recall@1
- type: maxsim_recall@3
value: 0.38
name: Maxsim Recall@3
- type: maxsim_recall@5
value: 0.42
name: Maxsim Recall@5
- type: maxsim_recall@10
value: 0.56
name: Maxsim Recall@10
- type: maxsim_ndcg@10
value: 0.3539147678833996
name: Maxsim Ndcg@10
- type: maxsim_mrr@10
value: 0.29019047619047617
name: Maxsim Mrr@10
- type: maxsim_map@100
value: 0.3044243083606632
name: Maxsim Map@100
- task:
type: multi-vector-information-retrieval
name: Multi Vector Information Retrieval
dataset:
name: NanoSciFact
type: NanoSciFact
metrics:
- type: maxsim_accuracy@1
value: 0.48
name: Maxsim Accuracy@1
- type: maxsim_accuracy@3
value: 0.58
name: Maxsim Accuracy@3
- type: maxsim_accuracy@5
value: 0.6
name: Maxsim Accuracy@5
- type: maxsim_accuracy@10
value: 0.68
name: Maxsim Accuracy@10
- type: maxsim_precision@1
value: 0.48
name: Maxsim Precision@1
- type: maxsim_precision@3
value: 0.21333333333333332
name: Maxsim Precision@3
- type: maxsim_precision@5
value: 0.136
name: Maxsim Precision@5
- type: maxsim_precision@10
value: 0.078
name: Maxsim Precision@10
- type: maxsim_recall@1
value: 0.445
name: Maxsim Recall@1
- type: maxsim_recall@3
value: 0.565
name: Maxsim Recall@3
- type: maxsim_recall@5
value: 0.59
name: Maxsim Recall@5
- type: maxsim_recall@10
value: 0.67
name: Maxsim Recall@10
- type: maxsim_ndcg@10
value: 0.564998292690912
name: Maxsim Ndcg@10
- type: maxsim_mrr@10
value: 0.5397142857142857
name: Maxsim Mrr@10
- type: maxsim_map@100
value: 0.5383929411495326
name: Maxsim Map@100
- task:
type: multi-vector-information-retrieval
name: Multi Vector Information Retrieval
dataset:
name: NanoTouche2020
type: NanoTouche2020
metrics:
- type: maxsim_accuracy@1
value: 0.3877551020408163
name: Maxsim Accuracy@1
- type: maxsim_accuracy@3
value: 0.7755102040816326
name: Maxsim Accuracy@3
- type: maxsim_accuracy@5
value: 0.8775510204081632
name: Maxsim Accuracy@5
- type: maxsim_accuracy@10
value: 0.9795918367346939
name: Maxsim Accuracy@10
- type: maxsim_precision@1
value: 0.3877551020408163
name: Maxsim Precision@1
- type: maxsim_precision@3
value: 0.44897959183673464
name: Maxsim Precision@3
- type: maxsim_precision@5
value: 0.4408163265306122
name: Maxsim Precision@5
- type: maxsim_precision@10
value: 0.35510204081632657
name: Maxsim Precision@10
- type: maxsim_recall@1
value: 0.024481017655879133
name: Maxsim Recall@1
- type: maxsim_recall@3
value: 0.09602376403984346
name: Maxsim Recall@3
- type: maxsim_recall@5
value: 0.15246910845015463
name: Maxsim Recall@5
- type: maxsim_recall@10
value: 0.24076032744792322
name: Maxsim Recall@10
- type: maxsim_ndcg@10
value: 0.39199232237420195
name: Maxsim Ndcg@10
- type: maxsim_mrr@10
value: 0.5977324263038547
name: Maxsim Mrr@10
- type: maxsim_map@100
value: 0.2962394648624034
name: Maxsim Map@100
---
# BERT tiny multi-vector encoder trained on MS MARCO
This is a [Multi-Vector Encoder](https://www.sbert.net/docs/multi_vector_encoder/usage/usage.html) model finetuned in two stages from [prajjwal1/bert-tiny](https://huggingface.co/prajjwal1/bert-tiny) on the [msmarco-bm25](https://huggingface.co/datasets/sentence-transformers/msmarco-bm25) dataset using the [sentence-transformers](https://www.SBERT.net) library. It maps inputs to sequences of 128-dimensional token-level vectors and scores them with late interaction (MaxSim), useful for semantic search with late interaction.
## Model Details
### Model Description
- **Model Type:** Multi-Vector Encoder
- **Base model:** [prajjwal1/bert-tiny](https://huggingface.co/prajjwal1/bert-tiny)
- **Maximum Sequence Length:** 512 tokens
- **Maximum Query Length:** 32 tokens
- **Maximum Document Length:** 256 tokens
- **Output Dimensionality:** 128 dimensions
- **Similarity Function:** MaxSim
- **Supported Modality:** Text
- **Training Dataset:**
- [msmarco-bm25](https://huggingface.co/datasets/sentence-transformers/msmarco-bm25)
- **Language:** en
- **License:** mit
### Model Sources
- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
- **Documentation:** [Multi-Vector Encoder Documentation](https://www.sbert.net/docs/multi_vector_encoder/usage/usage.html)
- **Repository:** [Sentence Transformers on GitHub](https://github.com/huggingface/sentence-transformers)
- **Hugging Face:** [Multi-Vector Encoders on Hugging Face](https://huggingface.co/models?library=sentence-transformers&other=multi-vector)
### Full Model Architecture
```
MultiVectorEncoder(
(0): Transformer({'transformer_task': 'feature-extraction', 'modality_config': {'text': {'method': 'forward', 'method_output_name': 'last_hidden_state'}}, 'module_output_name': 'token_embeddings', 'query_length': 32, 'document_length': 256, 'query_expansion': {'strategy': 'min', 'attend': False, 'token': None, 'length': 32}, 'architecture': 'BertModel'})
(1): Dense({'in_features': 128, 'out_features': 128, 'bias': False, 'activation_function': 'torch.nn.modules.linear.Identity', 'module_input_name': 'token_embeddings', 'module_output_name': 'token_embeddings'})
(2): MultiVectorMask({'skiplist_words': [], 'skiplist_tasks': ['document'], 'keep_only_token_ids': None})
(3): Normalize({'module_input_name': 'token_embeddings', 'module_output_name': 'token_embeddings'})
)
```
## Usage
### Direct Usage (Sentence Transformers)
First install the Sentence Transformers library:
```bash
pip install -U sentence-transformers
```
Then you can load this model and run inference.
```python
from sentence_transformers import MultiVectorEncoder
# Download from the 🤗 Hub
model = MultiVectorEncoder("multi-vector-encoder-testing/bert-tiny-multi-vector")
# Run inference: each input becomes a sequence of per-token vectors (variable length).
queries = [
'calories in kirkland ravioli',
]
documents = [
'There are 140 calories in a 4 pieces serving of Kirkland Signature Four Cheese Ravioli. Calorie breakdown: 45% fat, 31% carbs, 24% protein.',
'There are 140 calories in a 4 pieces serving of Kirkland Signature Four Cheese Ravioli. Calorie breakdown: 45% fat, 31% carbs, 24% protein.',
'Current Local Time: Cleveland, Ohio is in the Eastern Time Zone: The Current Time in Cleveland, Ohio is: Thursday 1/18/2018 10:41 PM EST Cleveland, Ohio is in the Eastern Time Zone',
]
query_embeddings = model.encode_query(queries)
document_embeddings = model.encode_document(documents)
print(query_embeddings[0].shape, document_embeddings[0].shape)
# (32, 128) (39, 128)
# Get the MaxSim similarity scores
similarities = model.similarity(query_embeddings, document_embeddings)
print(similarities)
# tensor([[25.4110, 25.4110, 8.3390]])
```
## Evaluation
### Metrics
#### Multi Vector Information Retrieval
* Datasets: `NanoMSMARCO`, `NanoNQ`, `NanoFiQA2018`, `NanoClimateFEVER`, `NanoDBPedia`, `NanoFEVER`, `NanoFiQA2018`, `NanoHotpotQA`, `NanoMSMARCO`, `NanoNFCorpus`, `NanoNQ`, `NanoQuoraRetrieval`, `NanoSCIDOCS`, `NanoArguAna`, `NanoSciFact` and `NanoTouche2020`
* Evaluated with [MultiVectorInformationRetrievalEvaluator](https://sbert.net/docs/package_reference/multi_vector_encoder/evaluation.html#sentence_transformers.multi_vector_encoder.evaluation.MultiVectorInformationRetrievalEvaluator)
| Metric | NanoMSMARCO | NanoNQ | NanoFiQA2018 | NanoClimateFEVER | NanoDBPedia | NanoFEVER | NanoHotpotQA | NanoNFCorpus | NanoQuoraRetrieval | NanoSCIDOCS | NanoArguAna | NanoSciFact | NanoTouche2020 |
|:--------------------|:------------|:---------|:-------------|:-----------------|:------------|:-----------|:-------------|:-------------|:-------------------|:------------|:------------|:------------|:---------------|
| maxsim_accuracy@1 | 0.16 | 0.28 | 0.26 | 0.18 | 0.62 | 0.56 | 0.72 | 0.42 | 0.74 | 0.26 | 0.18 | 0.48 | 0.3878 |
| maxsim_accuracy@3 | 0.32 | 0.4 | 0.4 | 0.3 | 0.78 | 0.72 | 0.9 | 0.52 | 0.88 | 0.42 | 0.38 | 0.58 | 0.7755 |
| maxsim_accuracy@5 | 0.42 | 0.48 | 0.48 | 0.34 | 0.84 | 0.82 | 0.92 | 0.52 | 0.9 | 0.52 | 0.42 | 0.6 | 0.8776 |
| maxsim_accuracy@10 | 0.7 | 0.66 | 0.58 | 0.5 | 0.94 | 0.86 | 0.96 | 0.6 | 0.92 | 0.74 | 0.56 | 0.68 | 0.9796 |
| maxsim_precision@1 | 0.16 | 0.28 | 0.26 | 0.18 | 0.62 | 0.56 | 0.72 | 0.42 | 0.74 | 0.26 | 0.18 | 0.48 | 0.3878 |
| maxsim_precision@3 | 0.1067 | 0.1333 | 0.18 | 0.1 | 0.4733 | 0.2467 | 0.4133 | 0.3267 | 0.36 | 0.18 | 0.1267 | 0.2133 | 0.449 |
| maxsim_precision@5 | 0.084 | 0.096 | 0.132 | 0.076 | 0.448 | 0.172 | 0.268 | 0.268 | 0.228 | 0.152 | 0.084 | 0.136 | 0.4408 |
| maxsim_precision@10 | 0.07 | 0.066 | 0.08 | 0.058 | 0.392 | 0.092 | 0.148 | 0.224 | 0.12 | 0.118 | 0.056 | 0.078 | 0.3551 |
| maxsim_recall@1 | 0.16 | 0.27 | 0.1229 | 0.0917 | 0.0521 | 0.5267 | 0.36 | 0.0447 | 0.654 | 0.054 | 0.18 | 0.445 | 0.0245 |
| maxsim_recall@3 | 0.32 | 0.39 | 0.251 | 0.13 | 0.117 | 0.6767 | 0.62 | 0.0718 | 0.8587 | 0.11 | 0.38 | 0.565 | 0.096 |
| maxsim_recall@5 | 0.42 | 0.46 | 0.3117 | 0.16 | 0.1668 | 0.7833 | 0.67 | 0.0835 | 0.886 | 0.154 | 0.42 | 0.59 | 0.1525 |
| maxsim_recall@10 | 0.7 | 0.61 | 0.387 | 0.2383 | 0.2876 | 0.8233 | 0.74 | 0.1061 | 0.9127 | 0.24 | 0.56 | 0.67 | 0.2408 |
| **maxsim_ndcg@10** | **0.3859** | **0.43** | **0.3027** | **0.1919** | **0.482** | **0.6793** | **0.684** | **0.2852** | **0.8355** | **0.2217** | **0.3539** | **0.565** | **0.392** |
| maxsim_mrr@10 | 0.292 | 0.3833 | 0.3604 | 0.2663 | 0.7217 | 0.6486 | 0.807 | 0.4765 | 0.8162 | 0.3871 | 0.2902 | 0.5397 | 0.5977 |
| maxsim_map@100 | 0.3049 | 0.3841 | 0.2447 | 0.1495 | 0.3543 | 0.6349 | 0.602 | 0.1259 | 0.8099 | 0.1561 | 0.3044 | 0.5384 | 0.2962 |
#### Multi Vector Nano BEIR
* Dataset: `NanoBEIR_mean`
* Evaluated with [MultiVectorNanoBEIREvaluator](https://sbert.net/docs/package_reference/multi_vector_encoder/evaluation.html#sentence_transformers.multi_vector_encoder.evaluation.MultiVectorNanoBEIREvaluator) with these parameters:
```json
{
"dataset_names": [
"msmarco",
"nq",
"fiqa2018"
],
"dataset_id": "sentence-transformers/NanoBEIR-en"
}
```
| Metric | Value |
|:--------------------|:-----------|
| maxsim_accuracy@1 | 0.2333 |
| maxsim_accuracy@3 | 0.3733 |
| maxsim_accuracy@5 | 0.46 |
| maxsim_accuracy@10 | 0.6467 |
| maxsim_precision@1 | 0.2333 |
| maxsim_precision@3 | 0.14 |
| maxsim_precision@5 | 0.104 |
| maxsim_precision@10 | 0.072 |
| maxsim_recall@1 | 0.1843 |
| maxsim_recall@3 | 0.3203 |
| maxsim_recall@5 | 0.3972 |
| maxsim_recall@10 | 0.5657 |
| **maxsim_ndcg@10** | **0.3729** |
| maxsim_mrr@10 | 0.3452 |
| maxsim_map@100 | 0.3112 |
#### Multi Vector Nano BEIR
* Dataset: `NanoBEIR_mean`
* Evaluated with [MultiVectorNanoBEIREvaluator](https://sbert.net/docs/package_reference/multi_vector_encoder/evaluation.html#sentence_transformers.multi_vector_encoder.evaluation.MultiVectorNanoBEIREvaluator) with these parameters:
```json
{
"dataset_names": [
"climatefever",
"dbpedia",
"fever",
"fiqa2018",
"hotpotqa",
"msmarco",
"nfcorpus",
"nq",
"quoraretrieval",
"scidocs",
"arguana",
"scifact",
"touche2020"
],
"dataset_id": "sentence-transformers/NanoBEIR-en"
}
```
| Metric | Value |
|:--------------------|:-----------|
| maxsim_accuracy@1 | 0.4037 |
| maxsim_accuracy@3 | 0.5673 |
| maxsim_accuracy@5 | 0.626 |
| maxsim_accuracy@10 | 0.7446 |
| maxsim_precision@1 | 0.4037 |
| maxsim_precision@3 | 0.2545 |
| maxsim_precision@5 | 0.1988 |
| maxsim_precision@10 | 0.1429 |
| maxsim_recall@1 | 0.2297 |
| maxsim_recall@3 | 0.3528 |
| maxsim_recall@5 | 0.4044 |
| maxsim_recall@10 | 0.5012 |
| **maxsim_ndcg@10** | **0.4468** |
| maxsim_mrr@10 | 0.5067 |
| maxsim_map@100 | 0.3773 |
## Training Details
### Training Dataset
#### msmarco-bm25
* Dataset: [msmarco-bm25](https://huggingface.co/datasets/sentence-transformers/msmarco-bm25) at [ce8a493](https://huggingface.co/datasets/sentence-transformers/msmarco-bm25/tree/ce8a493a65af5e872c3c92f72a89e2e99e175f02)
* Size: 501,907 training samples
* Columns: query, positive, and negative
* Approximate statistics based on the first 100 samples:
| | query | positive | negative |
|:---------|:---------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|
| type | string | string | string |
| modality | text | text | text |
| details | - min: 4 tokens
- mean: 8.81 tokens
- max: 16 tokens
| - min: 25 tokens
- mean: 78.08 tokens
- max: 174 tokens
| - min: 22 tokens
- mean: 76.59 tokens
- max: 180 tokens
|
* Samples:
| query | positive | negative |
|:-------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| sociopath define | Updated September 08, 2016. Both psychopaths and sociopaths are defined as someone who is suffering from Antisocial Personality Disorder. Both groups show a pervasive pattern of disregard for the rights and feelings of others. There are, however, subtle differences between the two groups. | Define sociopath. sociopath synonyms, sociopath pronunciation, sociopath translation, English dictionary definition of sociopath. n. A psychopath or a person with antisocial personality disorder. so′ci·o·path′ic adj. so′ci·op′a·thy n. n psychiatry another name for psychopath... |
| what county is tarrytown ny in | ABOUT US. The Music Hall, an 1885 landmark in Tarrytown, NY is Westchester County's oldest theater and one of the region's busiest music venues, welcoming 85,000 visitors every year, including tens of thousands of children. Please complete all required fields! | Tarrytown, NY Other Information. 1 Located in WESTCHESTER County, New York. 2 Tarrytown, NY is also known as: 3 N TARRYTOWN, NY. NORTH TARRYTOWN, 1 NY. PHILIPSE MANOR, 2 NY. POCANTICO HILLS, 3 NY. SLEEPY HOLLOW, NY. SLEEPY HOLLOW MANOR, NY. |
| what temperature do you grill a t-bone at | Step 2. Move your T-bones to the medium heat side of your grill and continue grilling. If you like your T-bone medium rare, grill for four to five minutes on each side or until a meat thermometer reads 130 to 140 degrees Fahrenheit.For a medium steak, grill six to seven minutes per side or until a meat thermometer reads 140 to 150 degrees.iming and technique are the keys to grilling a 1-inch-thick T-bone steak to perfection. This thicker cut requires different treatment from a T-bone, for example, 1/2- to 3/4-inch thick. | Preheat your grill using two temperature settings. If you are using a gas grill, set one side to high and the other to a medium setting, then close the lid for 10 to 15 minutes.iming and technique are the keys to grilling a 1-inch-thick T-bone steak to perfection. This thicker cut requires different treatment from a T-bone, for example, 1/2- to 3/4-inch thick. |
* Loss: [MultiVectorMultipleNegativesRankingLoss](https://sbert.net/docs/package_reference/multi_vector_encoder/losses.html#multivectormultiplenegativesrankingloss) with these parameters:
```json
{
"scale": 1.0,
"similarity_fct": "colbert_scores",
"mini_batch_size": null,
"score_mini_batch_size": null,
"gather_across_devices": false
}
```
### Evaluation Dataset
#### msmarco-bm25
* Dataset: [msmarco-bm25](https://huggingface.co/datasets/sentence-transformers/msmarco-bm25) at [ce8a493](https://huggingface.co/datasets/sentence-transformers/msmarco-bm25/tree/ce8a493a65af5e872c3c92f72a89e2e99e175f02)
* Size: 1,024 evaluation samples
* Columns: query, positive, and negative
* Approximate statistics based on the first 100 samples:
| | query | positive | negative |
|:---------|:---------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|
| type | string | string | string |
| modality | text | text | text |
| details | - min: 4 tokens
- mean: 8.65 tokens
- max: 15 tokens
| - min: 21 tokens
- mean: 80.76 tokens
- max: 174 tokens
| - min: 16 tokens
- mean: 79.88 tokens
- max: 224 tokens
|
* Samples:
| query | positive | negative |
|:----------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| what is the bottom lip piercing called | 1 Standard Lip Piercing – This is a single piercing done off centered on the lower lip. 2 A captive bead ring (CBR) or labret stud can be worn. 3 Monroe Piercing – This is a single piercing done on the left side of the upper lip and is named for the mole on Marilyn Monroe’s lip. 4 Usually a labret stud is worn in this piercing. | Also known as lower-lip piercing or bottom lip piercing .The labret piercing is placed at the labrum (below bottom lip, above chin). Popular among men and women, this style looks super cool and trendy. |
| what are the mind and body | This is known as dualism. Dualism is the view that the mind and body both exist. There are two basic types of dualism: o Descartes dualism: The view that the mind and body function separately, without interchange. o Cartesian dualism argues that there is a two-way interaction between mental and physical substances. Dualism is in contrast to monism that states the mind and body are the same thing. | Quotes About What Matters In Life. “What is in your mind position or disposition your mind, body and spirit in the best or worst way. What you are yet to accept into your mind exposes your mind to and keep your mind on what you are yet to accept and what has not yet come into your mind least controls your mind, body and spirit. Browse By Tag. |
| what breed of dogs have green eyes | Best Answer: There are many dog breeds that CAN have green eyes, such as Australian Shepherds, Border Collies, Siberian Huskies, and others, but it is an uncommon occurrence. However it won't be a bright green like a cat's eye. It'll be a somewhat subdued shade of blueish-grey with green overtones. | What are some dog breeds that have or can have green eyes? What breed is this dog? What is the breed of a dog, which looks like a fox and has light blue eyes, called? Rohit Akut, love and respect animals be friendly have had lots of different pets.. |
* Loss: [MultiVectorMultipleNegativesRankingLoss](https://sbert.net/docs/package_reference/multi_vector_encoder/losses.html#multivectormultiplenegativesrankingloss) with these parameters:
```json
{
"scale": 1.0,
"similarity_fct": "colbert_scores",
"mini_batch_size": null,
"score_mini_batch_size": null,
"gather_across_devices": false
}
```
### Training Hyperparameters
#### Non-Default Hyperparameters
- `per_device_train_batch_size`: 128
- `max_steps`: 10000
- `learning_rate`: 1e-05
- `warmup_steps`: 0.05
- `weight_decay`: 0.01
- `bf16`: True
- `disable_tqdm`: True
- `per_device_eval_batch_size`: 32
- `load_best_model_at_end`: True
- `seed`: 12
- `batch_sampler`: no_duplicates
#### All Hyperparameters
Click to expand
- `per_device_train_batch_size`: 128
- `num_train_epochs`: 3.0
- `max_steps`: 10000
- `learning_rate`: 1e-05
- `lr_scheduler_type`: linear
- `lr_scheduler_kwargs`: None
- `warmup_steps`: 0.05
- `optim`: adamw_torch_fused
- `optim_args`: None
- `weight_decay`: 0.01
- `adam_beta1`: 0.9
- `adam_beta2`: 0.999
- `adam_epsilon`: 1e-08
- `optim_target_modules`: None
- `gradient_accumulation_steps`: 1
- `average_tokens_across_devices`: True
- `max_grad_norm`: 1.0
- `label_smoothing_factor`: 0.0
- `bf16`: True
- `fp16`: False
- `bf16_full_eval`: False
- `fp16_full_eval`: False
- `tf32`: None
- `gradient_checkpointing`: False
- `gradient_checkpointing_kwargs`: None
- `torch_compile`: False
- `torch_compile_backend`: None
- `torch_compile_mode`: None
- `use_liger_kernel`: False
- `liger_kernel_config`: None
- `use_cache`: False
- `neftune_noise_alpha`: None
- `torch_empty_cache_steps`: None
- `auto_find_batch_size`: False
- `log_on_each_node`: True
- `logging_nan_inf_filter`: True
- `include_num_input_tokens_seen`: no
- `log_level`: passive
- `log_level_replica`: warning
- `disable_tqdm`: True
- `project`: huggingface
- `trackio_space_id`: None
- `trackio_bucket_id`: None
- `trackio_static_space_id`: None
- `per_device_eval_batch_size`: 32
- `prediction_loss_only`: True
- `eval_on_start`: False
- `eval_do_concat_batches`: True
- `eval_use_gather_object`: False
- `eval_accumulation_steps`: None
- `include_for_metrics`: []
- `batch_eval_metrics`: False
- `save_only_model`: False
- `save_on_each_node`: False
- `enable_jit_checkpoint`: False
- `push_to_hub`: False
- `hub_private_repo`: None
- `hub_model_id`: None
- `hub_strategy`: every_save
- `hub_always_push`: False
- `hub_revision`: None
- `load_best_model_at_end`: True
- `ignore_data_skip`: False
- `restore_callback_states_from_checkpoint`: False
- `full_determinism`: False
- `seed`: 12
- `data_seed`: None
- `use_cpu`: False
- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
- `parallelism_config`: None
- `dataloader_drop_last`: False
- `dataloader_num_workers`: 0
- `dataloader_pin_memory`: True
- `dataloader_persistent_workers`: False
- `dataloader_prefetch_factor`: None
- `dataloader_multiprocessing_context`: None
- `dataloader_in_order`: True
- `remove_unused_columns`: True
- `label_names`: None
- `train_sampling_strategy`: random
- `length_column_name`: length
- `ddp_find_unused_parameters`: None
- `ddp_bucket_cap_mb`: None
- `ddp_broadcast_buffers`: False
- `ddp_static_graph`: None
- `ddp_backend`: None
- `ddp_timeout`: 1800
- `fsdp`: None
- `fsdp_config`: None
- `deepspeed`: None
- `debug`: []
- `skip_memory_metrics`: True
- `do_predict`: False
- `resume_from_checkpoint`: None
- `local_rank`: -1
- `prompts`: None
- `batch_sampler`: no_duplicates
- `multi_dataset_batch_sampler`: proportional
- `router_mapping`: {}
- `learning_rate_mapping`: {}
- `warmup_ratio`: None
- `max_length`: None
Click to expand
| Epoch | Step | Training Loss | Validation Loss | NanoMSMARCO_maxsim_ndcg@10 | NanoNQ_maxsim_ndcg@10 | NanoFiQA2018_maxsim_ndcg@10 | NanoBEIR_mean_maxsim_ndcg@10 | NanoClimateFEVER_maxsim_ndcg@10 | NanoDBPedia_maxsim_ndcg@10 | NanoFEVER_maxsim_ndcg@10 | NanoHotpotQA_maxsim_ndcg@10 | NanoNFCorpus_maxsim_ndcg@10 | NanoQuoraRetrieval_maxsim_ndcg@10 | NanoSCIDOCS_maxsim_ndcg@10 | NanoArguAna_maxsim_ndcg@10 | NanoSciFact_maxsim_ndcg@10 | NanoTouche2020_maxsim_ndcg@10 |
|:----------:|:--------:|:-------------:|:---------------:|:--------------------------:|:---------------------:|:---------------------------:|:----------------------------:|:-------------------------------:|:--------------------------:|:------------------------:|:---------------------------:|:---------------------------:|:---------------------------------:|:--------------------------:|:--------------------------:|:--------------------------:|:-----------------------------:|
| -1 | 0 | - | - | 0.4328 | 0.2992 | 0.2658 | 0.3999 | 0.1431 | 0.3914 | 0.6310 | 0.5766 | 0.2569 | 0.7976 | 0.2029 | 0.2863 | 0.5060 | 0.4096 |
| 0.0003 | 1 | 1.7377 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 0.0127 | 50 | 1.7342 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 0.0255 | 100 | 1.7067 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 0.0382 | 150 | 1.6564 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 0.0510 | 200 | 1.6343 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 0.0637 | 250 | 1.6082 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 0.0765 | 300 | 1.5952 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 0.0892 | 350 | 1.5606 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 0.1020 | 400 | 1.5329 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 0.1147 | 450 | 1.4977 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 0.1275 | 500 | 1.5205 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 0.1402 | 550 | 1.4602 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 0.1530 | 600 | 1.4465 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 0.1657 | 650 | 1.4251 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 0.1785 | 700 | 1.3911 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 0.1912 | 750 | 1.3776 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 0.2040 | 800 | 1.3530 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 0.2167 | 850 | 1.3297 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 0.2295 | 900 | 1.3348 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 0.2422 | 950 | 1.3423 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 0.2550 | 1000 | 1.2872 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 0.2677 | 1050 | 1.2880 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 0.2805 | 1100 | 1.2762 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 0.2932 | 1150 | 1.2545 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 0.3060 | 1200 | 1.2463 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 0.3187 | 1250 | 1.2492 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 0.3315 | 1300 | 1.2145 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 0.3442 | 1350 | 1.2369 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 0.3570 | 1400 | 1.1995 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 0.3697 | 1450 | 1.1950 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 0.3825 | 1500 | 1.2016 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 0.3952 | 1550 | 1.1622 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 0.4080 | 1600 | 1.1886 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 0.4207 | 1650 | 1.1866 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 0.4335 | 1700 | 1.1774 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 0.4462 | 1750 | 1.1462 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 0.4589 | 1800 | 1.1655 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 0.4717 | 1850 | 1.1309 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 0.4844 | 1900 | 1.1613 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 0.4972 | 1950 | 1.1465 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 0.5099 | 2000 | 1.1741 | 0.8207 | 0.3460 | 0.4138 | 0.2792 | 0.3463 | - | - | - | - | - | - | - | - | - | - |
| 0.5227 | 2050 | 1.1287 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 0.5354 | 2100 | 1.1325 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 0.5482 | 2150 | 1.1121 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 0.5609 | 2200 | 1.1046 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 0.5737 | 2250 | 1.1026 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 0.5864 | 2300 | 1.1245 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 0.5992 | 2350 | 1.1253 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 0.6119 | 2400 | 1.1051 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 0.6247 | 2450 | 1.0870 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 0.6374 | 2500 | 1.0775 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 0.6502 | 2550 | 1.0713 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 0.6629 | 2600 | 1.0946 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 0.6757 | 2650 | 1.0682 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 0.6884 | 2700 | 1.0537 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 0.7012 | 2750 | 1.0500 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 0.7139 | 2800 | 1.0920 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 0.7267 | 2850 | 1.0873 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 0.7394 | 2900 | 1.0598 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 0.7522 | 2950 | 1.0745 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 0.7649 | 3000 | 1.0587 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 0.7777 | 3050 | 1.0532 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 0.7904 | 3100 | 1.0609 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 0.8032 | 3150 | 1.0611 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 0.8159 | 3200 | 1.0592 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 0.8287 | 3250 | 1.0413 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 0.8414 | 3300 | 1.0224 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 0.8542 | 3350 | 1.0372 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 0.8669 | 3400 | 1.0544 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 0.8797 | 3450 | 0.9922 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 0.8924 | 3500 | 1.0215 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 0.9052 | 3550 | 1.0052 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 0.9179 | 3600 | 1.0061 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 0.9306 | 3650 | 1.0136 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 0.9434 | 3700 | 1.0236 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 0.9561 | 3750 | 0.9937 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 0.9689 | 3800 | 1.0128 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 0.9816 | 3850 | 1.0399 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 0.9944 | 3900 | 0.9840 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 1.0071 | 3950 | 0.9999 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 1.0199 | 4000 | 1.0204 | 0.7238 | 0.3782 | 0.4405 | 0.2881 | 0.3690 | - | - | - | - | - | - | - | - | - | - |
| 1.0326 | 4050 | 1.0075 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 1.0454 | 4100 | 1.0111 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 1.0581 | 4150 | 0.9972 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 1.0709 | 4200 | 1.0144 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 1.0836 | 4250 | 1.0054 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 1.0964 | 4300 | 1.0123 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 1.1091 | 4350 | 0.9976 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 1.1219 | 4400 | 0.9798 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 1.1346 | 4450 | 1.0313 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 1.1474 | 4500 | 0.9913 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 1.1601 | 4550 | 0.9911 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 1.1729 | 4600 | 0.9880 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 1.1856 | 4650 | 0.9834 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 1.1984 | 4700 | 0.9489 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 1.2111 | 4750 | 0.9462 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 1.2239 | 4800 | 0.9670 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 1.2366 | 4850 | 0.9766 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 1.2494 | 4900 | 0.9655 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 1.2621 | 4950 | 0.9525 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 1.2749 | 5000 | 0.9818 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 1.2876 | 5050 | 0.9699 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 1.3004 | 5100 | 0.9679 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 1.3131 | 5150 | 0.9810 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 1.3259 | 5200 | 0.9723 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 1.3386 | 5250 | 0.9660 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 1.3514 | 5300 | 0.9688 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 1.3641 | 5350 | 0.9701 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 1.3768 | 5400 | 0.9532 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 1.3896 | 5450 | 0.9817 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 1.4023 | 5500 | 0.9401 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 1.4151 | 5550 | 0.9399 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 1.4278 | 5600 | 0.9505 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 1.4406 | 5650 | 0.9515 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 1.4533 | 5700 | 0.9576 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 1.4661 | 5750 | 0.9672 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 1.4788 | 5800 | 0.9414 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 1.4916 | 5850 | 0.9355 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 1.5043 | 5900 | 0.9615 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 1.5171 | 5950 | 0.9436 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| **1.5298** | **6000** | **0.9647** | **0.6846** | **0.3859** | **0.4304** | **0.3025** | **0.373** | **-** | **-** | **-** | **-** | **-** | **-** | **-** | **-** | **-** | **-** |
| 1.5426 | 6050 | 0.9528 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 1.5553 | 6100 | 0.9359 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 1.5681 | 6150 | 0.9409 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 1.5808 | 6200 | 0.9534 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 1.5936 | 6250 | 0.9594 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 1.6063 | 6300 | 0.9496 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 1.6191 | 6350 | 0.9398 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 1.6318 | 6400 | 0.9368 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 1.6446 | 6450 | 0.9482 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 1.6573 | 6500 | 0.9393 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 1.6701 | 6550 | 0.9601 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 1.6828 | 6600 | 0.9297 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 1.6956 | 6650 | 0.9263 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 1.7083 | 6700 | 0.9391 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 1.7211 | 6750 | 0.9424 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 1.7338 | 6800 | 0.9357 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 1.7466 | 6850 | 0.9470 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 1.7593 | 6900 | 0.9315 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 1.7721 | 6950 | 0.9289 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 1.7848 | 7000 | 0.9206 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 1.7976 | 7050 | 0.9493 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 1.8103 | 7100 | 0.9530 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 1.8230 | 7150 | 0.9379 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 1.8358 | 7200 | 0.9349 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 1.8485 | 7250 | 0.9017 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 1.8613 | 7300 | 0.9407 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 1.8740 | 7350 | 0.9158 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 1.8868 | 7400 | 0.9412 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 1.8995 | 7450 | 0.9240 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 1.9123 | 7500 | 0.9258 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 1.9250 | 7550 | 0.9456 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 1.9378 | 7600 | 0.9428 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 1.9505 | 7650 | 0.9630 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 1.9633 | 7700 | 0.9452 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 1.9760 | 7750 | 0.9222 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 1.9888 | 7800 | 0.9288 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 2.0015 | 7850 | 0.9349 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 2.0143 | 7900 | 0.9355 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 2.0270 | 7950 | 0.9041 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 2.0398 | 8000 | 0.9093 | 0.6678 | 0.3805 | 0.4371 | 0.2995 | 0.3724 | - | - | - | - | - | - | - | - | - | - |
| 2.0525 | 8050 | 0.9139 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 2.0653 | 8100 | 0.9533 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 2.0780 | 8150 | 0.9314 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 2.0908 | 8200 | 0.9206 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 2.1035 | 8250 | 0.9299 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 2.1163 | 8300 | 0.9174 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 2.1290 | 8350 | 0.9039 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 2.1418 | 8400 | 0.9092 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 2.1545 | 8450 | 0.9086 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 2.1673 | 8500 | 0.9605 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 2.1800 | 8550 | 0.9296 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 2.1928 | 8600 | 0.9196 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 2.2055 | 8650 | 0.9146 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 2.2183 | 8700 | 0.9130 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 2.2310 | 8750 | 0.9037 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 2.2438 | 8800 | 0.9357 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 2.2565 | 8850 | 0.9313 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 2.2693 | 8900 | 0.9179 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 2.2820 | 8950 | 0.9597 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 2.2947 | 9000 | 0.9274 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 2.3075 | 9050 | 0.9092 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 2.3202 | 9100 | 0.9072 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 2.3330 | 9150 | 0.9166 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 2.3457 | 9200 | 0.8974 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 2.3585 | 9250 | 0.9166 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 2.3712 | 9300 | 0.9281 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 2.3840 | 9350 | 0.9292 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 2.3967 | 9400 | 0.9166 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 2.4095 | 9450 | 0.9265 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 2.4222 | 9500 | 0.9142 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 2.4350 | 9550 | 0.9131 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 2.4477 | 9600 | 0.8902 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 2.4605 | 9650 | 0.9464 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 2.4732 | 9700 | 0.9167 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 2.4860 | 9750 | 0.9122 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 2.4987 | 9800 | 0.9217 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 2.5115 | 9850 | 0.9245 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 2.5242 | 9900 | 0.8963 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 2.5370 | 9950 | 0.9256 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
| 2.5497 | 10000 | 0.9121 | 0.6630 | 0.3796 | 0.4370 | 0.3010 | 0.3725 | - | - | - | - | - | - | - | - | - | - |
| -1 | -1 | - | - | 0.3859 | 0.4300 | 0.3027 | 0.4468 | 0.1919 | 0.4820 | 0.6793 | 0.6840 | 0.2852 | 0.8355 | 0.2217 | 0.3539 | 0.5650 | 0.3920 |
* The bold row denotes the saved checkpoint.